今天开始学习lucene
在lib里面导入两个包 junit.jar lucene-core-3.50.jar
六步
首先建立索引Directory、IndexWriter两个前提
创建Document
为Dcument增加Field
用Writer写入Document
关闭writer
九步
首先建立Directory、IndexReader两个前提
其次用IndexReader获取IndexSearcher
QueryParse
Query
TopDocs
ScoreDocs
Document
关闭reader
创建在哪个域中搜索什么内容的query
最终目的还是得到Document
关闭reader
HelloLucene.java
package org.itat.test;
import java.io.File;
import java.io.FileReader;
import java.io.IOException;
import org.apache.commons.io.FileUtils;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.LockObtainFailedException;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.Version;
public class HelloLucene {
/**
* 建立是索引
*/
public void index() {
IndexWriter writer = null;
try {
// 1,创建索引Directory
// Directory directory = new RAMDirectory();放在内存中
Directory directory = FSDirectory.open(new File(
"e:/lucene/index_01"));// 放在硬盘中
// 2,创建IndexWriter
IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_35,
new StandardAnalyzer(Version.LUCENE_35));
writer = new IndexWriter(directory, iwc);
// 3,创建文档Document
Document document = null;
// 4,为Document添加域Field
File file = new File("e:/lucene/example");
for (File f : file.listFiles()) {
document = new Document();
//String content=FileUtils.readFileToString(f);
//System.out.println(content);
//commons-io-2.1.jar这个包很好用
//1.txt和2.txt合二为一了最后
document.add(new Field("content", new FileReader(f)));
document.add(new Field("filename", f.getName(),Field.Store.YES, Field.Index.NOT_ANALYZED));
document.add(new Field("path", f.getAbsolutePath(),Field.Store.YES, Field.Index.NOT_ANALYZED));
// 5,通过indexWriter吧文档添加到索引directory中
writer.addDocument(document);
}
} catch (CorruptIndexException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (LockObtainFailedException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} finally {
if (writer != null)
try {
writer.close();
} catch (CorruptIndexException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}
/**
* 搜索
*/
public void search() {
try {
// 1.创建Directory
Directory directory = FSDirectory.open(new File(
"e:/lucene/index_01"));
// 2.创建IndexReader
IndexReader reader = IndexReader.open(directory);
// 3.根据IndexReader创建IndexSercher
IndexSearcher searcher = new IndexSearcher(reader);
// 4.创建搜索的Query
// 创建parse来确定搜索文件的内容,第二个参数是搜索的域
QueryParser parser = new QueryParser(Version.LUCENE_35, "content",new StandardAnalyzer(Version.LUCENE_35));
// 创建query,表示搜索域为content包含的内容
Query query = parser.parse("java");
// 5.根据sercher搜索并返回TopDocs
TopDocs tds = searcher.search(query, 10);
// 6.根据TopDocs获取ScoreDoc对象
ScoreDoc sds[] = tds.scoreDocs;
for (ScoreDoc sd : sds) {
// 7.根据sercher对象和Scoredoc对象获取Document对象
Document d = searcher.doc(sd.doc);
// 8.根据Document对象获取需要的值
System.out.println(d.get("filename") + "[" + d.get("path")+ "]");
}
// 9.关闭reader
reader.close();
} catch (Exception e) {
e.printStackTrace();
// TODO: handle exception
}
}
}
TestLucene.java
package org.itat.test;
import org.junit.Test;
public class TestLucene {
@Test
public void testIndex()
{
HelloLucene helloLucene=new HelloLucene();
helloLucene.index();
}
@Test
public void testSearch()
{
HelloLucene helloLucene=new HelloLucene();
helloLucene.search();
}
}